Probit vs Logit

On 19 December 2018, S&P500 dropped 1.54%, the next day (20 December 2018), KLCI dropped 0.31%.  The linear and logit regression model published on 14 December 2018 (Read more here) predicted the KLCI would fall 0.37% and the chances of the drop are as high as 75%.  This shows that the quantitative approach is indeed decent. 

Besides logit model, one could also use a probit model to run similar analysis.  In the logit model the log odds of the outcome is modelled as a linear combination of the predictor variables.  Meanwhile, in the probit model, the inverse standard normal distribution of the probability is modelled as a linear combination of the predictors.

Chart 1 shows the probability plot for both logit and probit models.  Both models should give similar results.  The slight difference is logit model has fatter tail.

Chart 1

Table 1 is the summary of the probit regression with the estimated coefficients.  The p-values show that the slope is significant but the intercept is not significant.  However, the impact of the intercept to the estimated probability is about 0.5%, which is relatively small, and also the condition where X = 0 is not modelled in this setup.

Table 1

Logit Regression on Overnight S&P500 Performance Impact on KLCI

We often hear that overnight US stocks performance might have an impact on KLCI the next day.  But how shall we quantify this?  A simple linear regression could be used to estimate the KLCI performance based on overnight Wall Street results.  However, the goodness-of-fit is usually poor. 

Chart 1 and Table 1 shows the regression plot and ANOVA table for overnight S&P500 and next day’s KLCI index performance using daily closing data from November 2015 to December 2018.  The R² is low at 0.1237.  Nevertheless, the significant of the slope’s p-value suggests that there are positive correlation between S&P500 and KLCI.

Chart 1 

  

Table 1

Let’s ask the next question – what is the probability of the KLCI to close positively or negatively, given the performance of overnight S&P500?  To answer the question, we could use logistic regression (“logit”) to study the probability.  Logistic regression is used in various fields, including machine learning (Read more here).  It uses a logistic function to model a binary dependent variable.  The logistic function is constructed based on linear regression model.

Linear regression model is

In logit model, Y value is labelled as “1” if KLCI gain on the next day or labelled as “0” if KLCI loss on the next day.  X is the overnight S&P500 performance while b₀ and b₁ are the coefficients.

The probability of the function with given X value is

The coefficients are then estimated using Maximum Likelihood Estimation (MLE)

Table 2 shows the first 5 rows of the data and their respective equations while Table 3 is the summary of the logistic regression with the estimated coefficients.  The p-values show that the slope is significant but the intercept is not significant.  However, the impact of the intercept to the estimated probability is about 0.5%, which is relatively small, and also the condition where X = 0 is not modeled in this setup.

Table 2

Table 3

 

Now back to our question, what is the probability of the KLCI to close positively or negatively, given the performance of overnight S&P500?  Chart 2 is the probability of KLCI Gain/Loss on next day given overnight S&P500 performance.  The probability distribution shows that if overnight S&P500 gained 5%, it is almost 99% sure that KLCI will gain on the following day.  If overnight S&P500 gained 1%, the chance for KLCI to gain on the next day is around 70%.  What if overnight S&P500 loss 2%?  Then the probability of KLCI to close positively on the following day would be around 15%.

Chart 2

"Qualitative" Regression On KLCI

Common linear regression is quantitative in nature.  However, it could be used as qualitative measure under certain condition.  For example, suppose we want to examine the seasonality of stocks return, we could estimate the regression model using “dummy” variables as independent variables.  A “dummy” variable takes on a value of 1 if a particular condition is true and 0 if that condition is false.

Using the KLCI monthly closing return data from November 2011 to November 2018, we can estimate a regression including an intercept and 11 dummy variables, one for each of the first 11 months of the year.  The equation that we estimate is

Return_t = b₀ + b₁Jan_t + b₂Feb_t + … + b₁₁Nov_t + e_t

where each monthly dummy variable has a value of 1 when the month occurs and a value of 0 for other months.  The intercept b₀, measures the average return for KLCI in December because there is no dummy variable for December.

The following table shows the results of the regression.

The low R² suggests that a month-of-the-year effect in KLCI returns may not be very important for explaining KLCI returns.  However, the significance of F-Test is below the conventional level of 5%, which indicates that we cannot reject the null hypothesis that all of the coefficients jointly are equal to 0.  This means we could look at the seasonality effect on certain months that are statistically significant such as December (Intercept), May, June, August, September and November.  Amongst those months, only December has positive average return while other months have negative average returns.  Will the history repeat itself in December 2018, perhaps window dressing for this holiday season?

Reference:

CFA Program Level II Reading Assignment by Sanjiv R. Das, PhD, Richard A. DeFusco, PhD, CFA, Dennis W. Mcleavey, CFA, Jerald E. Pinto, PhD, CFA, and David E. Runkle, PhD, CFA

Financial Ratio Ranking: The Composite Method (Banking Sector)

One distinctive characteristic of banks is their asset composition.  Generally, non-financial companies’ assets are predominantly tangible assets, such as plants, properties and equipment.  While bank assets are predominantly financial assets such as loans and securities and their liabilities are primarily deposits.

Banks are also heavily regulated by authorities as such, capital, minimum liquidity, and the riskiness of assets must meet authorities’ requirements.

Hence, certain conventional financial ratios such as Gross Profit Margin, Inventory Turnover, Current Ratio and D/E etc are not relevant.

The most common rating approach for banks is “CAMELS”, an acronym of six components as follows:

Capital adequacy

Capital adequacy for banks is described in terms of the proportion of the bank’s assets funded with capital. For purposes of determining capital adequacy, a bank’s assets are adjusted based on their risk, with riskier assets requiring a higher weightage.

Asset quality

Asset quality pertains to the amount of existing and potential credit risk associated with a bank’s assets and focuses primarily on financial assets.

Management capabilities

Management capability is the ability to identify and control risk, including credit risk, market risk, operating risk, legal risk, and other risks.

Earnings sufficiency

Earning sufficiency means banks should ideally generate an amount of earnings to provide an adequate return on capital to their capital providers and specifically to reward their stockholders through capital appreciation and/or distribution of earnings.

Liquidity position

Adequate liquidity is essential for any type of entity. Banks’ systemic importance increases the importance of adequate liquidity. If a non-bank entity’s insufficient liquidity prevents it from paying a current liability, the impact would primarily affect the entity’s own supply chain.

Sensitivity to market risk

Banks’ operational sensitivity to interest rates, exchange rates, equity prices, or commodity prices are key to its financial strength.

Table 1 shows some selected ratios that fall within CAMELS rating methodology, amongst other:

Category	Financial Ratio
Capital Adequacy	Common Equity Tier (CET) 1 Capital Ratio;           Total Capital Ratio
Asset Quality	Gross Impaired Loan Ratio (GIL)
Management Capabilities	Cost to Income Ratio;           Efficiency Ratio
Earnings Sufficiency	Return On Equity (ROE)
Liquidity Positions	Liquidity Coverage Ratio (LCR);           Net Stable Funding Ratio (NSFR)
Sensitivity to Market Risk	Value at Risk (VaR)
Non-CAMELS
Liquidity	Loan to Deposit Ratio (LDR)
Valuation	Price to Book (PB)

Table 1.  Selected Financial Ratios for CAMELS and non-CAMELS rating methodology

The ratios for CAME are readily available in Annual Reports, but the "Liquidity Positions" and "Sensitivity to Market Risk" are not commonly reported in banks’ Annual Reports.  For instance, BASEL III (Read more here) requires banks to report LCR and NSFR on monthly basis but they are not disclosed in the Annual Report.  Also, VaR is not published in an annual report as well.  Thus, for retail investors to evaluate the ratios of bank stocks, both “Liquidity Positions” and “Sensitivity to Market Risk” categories are replaced with liquidity and valuation ratio such as LDR and PB.

Table 2 and 3 are some real-world examples of the above ratios based on eight commercial banks listed on Bursa Malaysia.  Readers are reminded not to rely solely on the brief financial ratio ranking for investment decision.

     Table 2. Selected Financial Ratios for eight commercial banks listed on Bursa Malaysia

Source:

Dynaquest Sdn. Bhd. STOCKBASE platform, except *.  See “Notes” at the end of this article for Copyrights details.

* Calculated based on latest Annual Report

Table 3.  Ranking based on Financial Ratios in Table 2

Reference:

Analysis of Financial Institutions by Jack T. Ciesielski, CPA, CFA, and Elaine Henry, PhD, CFA

Disclaimer:  The above analysis does not imply any buy or sell recommendation.  The author disclaims all liabilities arising from any use of the information contained in this article.

Disclosure: The author may have interest in the stocks of the companies in this article.

Notes:  The data are the property of Dynaquest Sdn. Bhd.  It is subject to Intellectual Property Rights and T&C.  Do not reproduce without the consent from Dynaquest Sdn. Bhd.  (The author has signed a “Data Sharing Agreement” with Dynaquest Sdn. Bhd., based on a “Data Sharing Fee”, to use the data from Dynaquest Sdn. Bhd.’s STOCKBASE platform in this blog.  The content of this blog in no way represents the views or opinions of Dynaquest Sdn. Bhd.)

Financial Ratio Ranking: The Composite Method (Electronics Sector)

In previous article, the composite ranking method using financial ratios were discussed based on Plantation sector (Read more here).  This week, Electronics sector is selected for discussion.

It is very common for electronics companies listed on Bursa Malaysia to maintain high cash position and low debt level.  Thus, certain financial ratio such as D/E and interest coverage ratio may not be meaningful.  As such, few ratios are replaced to focus more on the operating efficiency and free cash flow generation.

Also, financial ratios are computed using financial statements.  Different companies may have different approaches to recognize their costs.  For instance, MPI cost of sales is very high but their Selling, General & Administration (SG&A) costs are low.  As such, MPI’s gross margin is relatively low compared to its peers but its operating profit margin is on-par with its peers.  Thus, Gross Margin is replaced with EBITDA Margin for this analysis.

Source: Dynaquest Sdn. Bhd. STOCKBASE platform.  See “Notes” at the end of this article for Copyrights details.

Disclaimer:  The above analysis does not imply any buy or sell recommendation.  The author disclaims all liabilities arising from any use of the information contained in this article.

Disclosure: The author may have interest in the stocks of the companies in this article.

Notes:  The data are the property of Dynaquest Sdn. Bhd.  It is subject to Intellectual Property Rights and T&C.  Do not reproduce without the consent from Dynaquest Sdn. Bhd.  (The author has signed a “Data Sharing Agreement” with Dynaquest Sdn. Bhd., based on a “Data Sharing Fee”, to use the data from Dynaquest Sdn. Bhd.’s STOCKBASE platform in this blog.  The content of this blog in no way represents the views or opinions of Dynaquest Sdn. Bhd.)

Using Financial Ratio to Screen Stocks: The Composite Approach

Stocks selection is always a challenging task.  They are many stock screening tools available on the web but most of them have rather simple screening function based on dividend yield, PE or market capitalisation.  Financial ratio screening is also available but the screening process is on stand-alone basis and may not provide ranking information.

In stock analysis, financial ratios are very useful tools to gauge a company’s financial health, operating efficiency and earnings quality.  There are many categories of financial ratios such as Activity Ratios, Liquidity Ratios, Solvency Ratios, Profitability Ratios, Valuation Ratios and others.  Often, ratios from different categories may give contradicting messages.  This article will discuss a simple method to rank companies using various financial ratios, the “composite” way.

First, we shall identify the ratios that we would like to include in the ranking process.  The following ratios are chosen for illustration purposes only.

Category	Ratio	Interpretation
Activity Ratios	Current Assets turnover	Higher Better
	Total assets turnover	Higher Better
Liquidity Ratios	Current Ratio	Higher Better
	Operating Cash Flow to Debt	Higher Better
Solvency Ratios	Debt to Equity Ratio	Lower Better
	Interest Coverage	Higher Better
Profitability Ratios	Gross Profit Margin	Higher Better
	Net Profit Margin	Higher Better
	Return On Equity	Higher Better
Valuation Ratios	Price to Earnings	Lower Better

Next, we choose ten companies from the same sector.  For this article, we have chosen the Plantation Sector in Malaysia.  The following table shows the respective financial ratios for ten plantation companies listed on Bursa Malaysia.

Source: Dynaquest Sdn. Bhd. STOCKBASE platform except 1,000,000.00.  See “Notes” at the end of this article for Copyrights details.

* 1,000,000.00 was inserted for company which has zero debt to avoid "divide by zero issue"

Once the financial ratios are ready, we could rate it according to a scale from 10 (Favourable) to 1 (Least Favourable).

From the above table we could see that some companies may have scored well in certain ratios but performed poorly on other ratios.  For quick comparison purposes, we could then calculate the average rating for each company as depicted in the following table.

This method is useful for investors who would like a first cut screening before carrying out more detailed financial analysis.  Investors shall not make investment decision solely based on a ratio analysis as there are other factors that may impact prospects for any investment in plantation stocks.

Disclaimer:  The above analysis does not imply any buy or sell recommendation.  The author disclaims all liabilities arising from any use of the information contained in this article.

Disclosure: The author may have interest in the stocks of the companies in this article.

Notes:  The data are the property of Dynaquest Sdn. Bhd.  It is subject to Intellectual Property Rights and T&C.  Do not reproduce without the consent from Dynaquest Sdn. Bhd.  (The author has signed a “Data Sharing Agreement” with Dynaquest Sdn. Bhd., based on a “Data Sharing Fee”, to use the data from Dynaquest Sdn. Bhd.’s STOCKBASE platform in this blog.  The content of this blog in no way represents the views or opinions of Dynaquest Sdn. Bhd.)

Why Property Prices Are High?

Digress a bit this week...

Google Trends Search Term Data & Bitcoin Price

In previous article, KLCI movement was forecasted using Google Trends’ Data (Read more here).  This week, the relationship between Bitcoin Price and its search frequency on Google will be discussed.

Google Trends (Read more here) is a website by Google that analyzes the popularity of top search queries in Google Search across various regions and languages. The website uses graphs to compare the search volume of different queries over time (source: Wikipedia).

The following chart shows the relative query frequency of the term “Bitcoin” in Google Search and the Bitcoin price from Jan 2016 to Sep 2018.  The blue line is the normalized “Bitcoin” search term frequency while the orange line is the normalized Bitcoin price.  There is a very strong correlation between these two parameters.  This could be due to Bitcoin traders or investors who are internet savvy at the same time.  Speculators may monitor the “Bitcoin” search term frequency to predict the next movement of the Bitcoin price.

Ringgit Malaysia (RM) Exchange Rate After GE14

In previous article, RM exchange rate movement based on Brent Crude Oil and other political factors was demonstrated (Read more here).  Today, let's look at the impact of GE14 to RM.

The chart below shows the relationship between RM and Brent Crude Oil.  The scattered blue dots are the actual data of USD/RM corresponding to respective Brent Crude Oil price from July 2005 to July 2015 while the scattered red dots are the actual data of USD/RM corresponding to respective Brent Crude Oil price from August 2015 to December 2017.  The green dots are pre-GE14 data while the yellow dots are post-GE14 data in 2018.

Before the 1MDB scandal was exposed, RM was strongly correlated with oil price.  This is shown by the blue dashed curve (July 2005 – July 2017, R² = 0.74).  After the 1MDB scandal was exposed, RM was weakened to about one standard deviation from the historical trend.  It was trading on the red dashed curve four month before the GE14.  However, RM was further weakened to 1.5 standard deviation curve (dashed yellow curve) immediate after GE14.  This could be due to the additional negative news exposed by the newly elected Government.

Moving forward, RM is expected to trade along the yellow curve before Malaysia finds a sound solution to solve its financial and economic issues.  According to EIA and OECD data, oil price is projected to trade around USD69 – 73 per barrel in 2018 (Read more here).  This suggests the RM will be trading in the range of RM4.05 to RM4.15.  Meanwhile, on 4^th September, Standard Chartered Bank suggested the ringgit will trade at RM4.0 against the USD by end of 2018 and RM4.1 by end of 2019 (Read more here).

Source: Knoema