#1. As the manager of the trading desk at an investment management firm, you have noticed that the average bidask spreads of different Nasdaq-listed stocks can vary widely. You have formulated the hypothesis that Nasdaq stocks percentage bidask spreads are related to the number of market makers and the companys stock market capitalization. You have decided to investigate your hypothesis using multiple regression analysis. You specify a regression model in which the dependent variable measures the percentage bidask spread and the independent variables measure the number of market makers and the companys stock market capitalization. The regression is estimated using data for 1,819 Nasdaq-listed stocks. Based on earlier published research exploring bidask spreads, you express the dependent and independent variables as natural logarithms, a so-called log-log regression model. A log-log regression model may be appropriate when one believes that proportional changes in the dependent variable bear a constant relationship to proportional changes in the independent variable(s). You formulate the multiple regression: Yi =b0 +b1X1i +b2X2i +i where: Yi = the natural logarithm of (bidask spread/stock price) for stock i X1i = the natural logarithm of the number of Nasdaq market makers for stock i X2i = the natural logarithm of the market capitalization (measured in millions of dollars) of company i A.) How much do you expect bid-ask spread/stock price to increase or decrease by? B.) You suspect that the greater the number of market makers, the smaller the percentage bidask spread. Formulate a null hypothesis and alternative hypothesis at a .01 significance level? C.) You also believe that the stocks of companies with higher market capitalization may have more-liquid markets, tending to lower percentage bidask spreads. Formulate a null hypothesis and alternative hypothesis at a .01 significance level? D.) Explain the overall significance of the regression? E.) What is the predicted bidask spread as a percent of the stock price? Results from Regressing ln(BidAsk Spread/Price) on ln(Number of Market Makers) and ln(Market Cap)